Search Results for author: Johannes Kofler

Found 6 papers, 4 papers with code

Residual Neural Networks for the Prediction of Planetary Collision Outcomes

1 code implementation9 Oct 2022 Philip M. Winter, Christoph Burger, Sebastian Lehner, Johannes Kofler, Thomas I. Maindl, Christoph M. Schäfer

We formulate the ML task as a multi-task regression problem, allowing simple, yet efficient training of ML models for collision treatment in an end-to-end manner.

Out-of-Distribution Generalization

Few-Shot Learning by Dimensionality Reduction in Gradient Space

1 code implementation7 Jun 2022 Martin Gauch, Maximilian Beck, Thomas Adler, Dmytro Kotsur, Stefan Fiel, Hamid Eghbal-zadeh, Johannes Brandstetter, Johannes Kofler, Markus Holzleitner, Werner Zellinger, Daniel Klotz, Sepp Hochreiter, Sebastian Lehner

We introduce SubGD, a novel few-shot learning method which is based on the recent finding that stochastic gradient descent updates tend to live in a low-dimensional parameter subspace.

Dimensionality Reduction Few-Shot Learning

Supervised machine learning classification for short straddles on the S&P500

no code implementations26 Apr 2022 Alexander Brunhuemer, Lukas Larcher, Philipp Seidl, Sascha Desmettre, Johannes Kofler, Gerhard Larcher

In this working paper we present our current progress in the training of machine learning models to execute short option strategies on the S&P500.

BIG-bench Machine Learning

Bell violation with entangled photons, free of the coincidence-time loophole

1 code implementation3 Sep 2013 Jan-Åke Larsson, Marissa Giustina, Johannes Kofler, Bernhard Wittmann, Rupert Ursin, Sven Ramelow

A recent experiment [Giustina et al, Nature, 2013] violated a Bell inequality without being vulnerable to the detection (or fair-sampling) loophole, therefore not needing the fair-sampling assumption.

Quantum Physics

Cannot find the paper you are looking for? You can Submit a new open access paper.